# FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos

arXiv: https://arxiv.org/abs/1603.08968 · HTML: https://mlsanity.com/paper/1603.08968/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2016.

## Built on by (most cited first, 10 of 10)

- [Efficient Video Compression via Content-Adaptive Super-Resolution](https://mlsanity.com/paper/2104.02322/) (2021)
- [Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2308.05022/) (2023)
- [Gemino: Practical and Robust Neural Compression for Video Conferencing](https://mlsanity.com/paper/2209.10507/) (2022)
- [Real-Time Super-Resolution System of 4K-Video Based on Deep Learning](https://mlsanity.com/paper/2107.05307/) (2021)
- [A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution](https://mlsanity.com/paper/2210.08229/) (2022)
- [Plug-and-Play Versatile Compressed Video Enhancement](https://mlsanity.com/paper/2504.15380/) (2025)
- [Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks](https://mlsanity.com/paper/2208.09195/) (2022)
- [BiSwift: Bandwidth Orchestrator for Multi-Stream Video Analytics on Edge](https://mlsanity.com/paper/2312.15740/) (2023)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media](https://mlsanity.com/paper/2609.18634/) (2026)

## Abstract (arXiv)

State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a framework to accelerate any SR algorithm applied to compressed videos. FAST exploits the temporal correlation between adjacent frames such that SR is only applied to a subset of frames; SR pixels are then transferred to the other frames. The transferring process has negligible computation cost as it uses information already embedded in the compressed video (e.g., motion vectors and residual). Adaptive processing is used to retain accuracy when the temporal correlation is not present (e.g., occlusions). FAST accelerates state-of-the-art SR algorithms by up to 15x with a visual quality loss of 0.2dB. FAST is an important step towards real-time SR algorithms for ultra-HD displays and energy constrained devices (e.g., phones and tablets).